octo-models/octo
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
PythonMIT
Stargazers
- 0to1
- Abivishaq
- albertww
- anshulrai
- ases200q2Singapore
- asmith26
- caelanNVIDIA Research
- dexter1691Georgia Tech
- dibyaghosh
- edwhu@microsoft
- fabawiUniversity of Hamburg
- fabiohtoSão Paulo
- hdvrai
- jijamw
- joeljangUniversity of Washington
- junjungoal
- kidmam
- kir0ul
- leonvolMunich, Germany
- mstoelzleMIT LIDS
- nicehiro@romi-lab
- ojh6404JSK Lab, UTokyo
- omarirfaToronto, Canada
- philippe-eecsGen AI, Meta
- pushkalkataraUnited States
- ray8828Philadelphia
- rperezdattariTU Delft
- shuixing85
- tomchapinPhase Interactive
- traversaroItalian Institute of Technology
- Umar-Azam
- wbthomason@bdaiinstitute
- wilson1yanUniversity of California, Berkeley
- wuyongyiLambdaX
- xuanlinli17San Diego, CA
- youliangtanNvidia